AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery

Ali Hatamizadeh, Debleena Sengupta, Demetri Terzopoulos

ECCV 2020 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 58 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add per-pixel learned lambda parameter maps (vs constant lambda) (ablation)TDAC · Vaihingen (single-instance)mIoU: 83.79 -> 89.16Improved
add per-pixel learned lambda parameter maps (vs constant lambda) (ablation)TDAC · Bing Huts (single-instance)Boundary F: 48.25 -> 53.50Improved
add per-pixel learned lambda parameter maps (vs constant lambda) (ablation)TDAC · Vaihingen (multiple-instance)mIoU: 83.30 -> 91.10Improved
add per-pixel learned lambda parameter maps (vs constant lambda) (ablation)TDAC · Bing Huts (multiple-instance)mIoU: 68.34 -> 71.30Improved
add end-to-end trained constant-lambda ACM (Chan-Vese) on top of the CNN backboneFCN (Ours backbone) · Vaihingen (single-instance)mIoU: 81.10 -> 83.79Improved
add end-to-end trained constant-lambda ACM (Chan-Vese) on top of the CNN backboneFCN (Ours backbone) · Bing Huts (multiple-instance)mIoU: 60.31 -> 68.34Improved
add end-to-end trained constant-lambda ACM (Chan-Vese) on top of the CNN backboneFCN (Ours backbone) · Bing Huts (single-instance)mIoU: 74.09 -> 73.02Mixed
replace DarNet with TDAC (CNN+ACM jointly trained)DarNet · Vaihingen (single-instance)mIoU: 88.20 -> 89.16Improved
replace DarNet with TDAC (CNN+ACM jointly trained)DarNet · Bing Huts (single-instance)mIoU: 75.20 -> 80.39Improved
replace Mask R-CNN backbone FCN with TDACFCN (Mask R-CNN) · Vaihingen (multiple-instance)mIoU: 79.42 -> 91.10Improved
vary convolutional filter size (too small or too large) (ablation)TDAC · Vaihingen and Bing HutsmIoUMixed
increase number of ACM iterations L beyond a threshold (ablation)TDAC · Vaihingen and Bing HutsmIoUNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy